# Evaluating Multiview Object Consistency in Humans and Image Models

arXiv: https://arxiv.org/abs/2409.05862 · HTML: https://mlsanity.com/paper/2409.05862/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 37 references that are in the map.
- First posted on arXiv 9 Sep 2024.

## Builds on (most cited first, 3 of 3)

- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Probing the 3D Awareness of Visual Foundation Models](https://mlsanity.com/paper/2404.08636/) (2024)
- [Explanatory models in neuroscience: Part 1 -- taking mechanistic abstraction seriously](https://mlsanity.com/paper/2104.01490/) (2021)

## Built on by (most cited first, 13 of 13)

- [Cameras as Relative Positional Encoding](https://mlsanity.com/paper/2507.10496/) (2025)
- [DepthCues: Evaluating Monocular Depth Perception in Large Vision Models](https://mlsanity.com/paper/2411.17385/) (2024)
- [How Much 3D Do Video Foundation Models Encode?](https://mlsanity.com/paper/2512.19949/) (2025)
- [Better artificial intelligence does not mean better models of biology](https://mlsanity.com/paper/2504.16940/) (2025)
- [VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs](https://mlsanity.com/paper/2507.13361/) (2025)
- [Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT](https://mlsanity.com/paper/2505.24182/) (2025)
- [CHART-6: Human-Centered Evaluation of Data Visualization Understanding in Vision-Language Models](https://mlsanity.com/paper/2505.17202/) (2025)
- [Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation](https://mlsanity.com/paper/2511.22121/) (2025)
- [Human-level 3D shape perception emerges from multi-view learning](https://mlsanity.com/paper/2602.17650/) (2026)
- [Do multimodal models imagine electric sheep?](https://mlsanity.com/paper/2605.09693/) (2026)
- [Accuracy Does Not Guarantee Human-Likeness: Cross-Domain Human-Centered Benchmark in Monocular Depth Estimation](https://mlsanity.com/paper/2512.08163/) (2025)
- [Spectral Probing of Feature Upsamplers in 2D-to-3D Scene Reconstruction](https://mlsanity.com/paper/2603.05787/) (2026)
- [NICE FACT: Diagnosing and Calibrating VLMs in Quantitative Reasoning for Kinematic Physics](https://mlsanity.com/paper/2605.08452/) (2026)

## Abstract (arXiv)

We introduce a benchmark to directly evaluate the alignment between human observers and vision models on a 3D shape inference task. We leverage an experimental design from the cognitive sciences which requires zero-shot visual inferences about object shape: given a set of images, participants identify which contain the same/different objects, despite considerable viewpoint variation. We draw from a diverse range of images that include common objects (e.g., chairs) as well as abstract shapes (i.e., procedurally generated `nonsense' objects). After constructing over 2000 unique image sets, we administer these tasks to human participants, collecting 35K trials of behavioral data from over 500 participants. This includes explicit choice behaviors as well as intermediate measures, such as reaction time and gaze data. We then evaluate the performance of common vision models (e.g., DINOv2, MAE, CLIP). We find that humans outperform all models by a wide margin. Using a multi-scale evaluation approach, we identify underlying similarities and differences between models and humans: while human-model performance is correlated, humans allocate more time/processing on challenging trials. All images, data, and code can be accessed via our project page.